Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Off-policy Evaluation on D4RL Half Cheetah Synthetic via VAE (test)
Loading...
1,820.79
Confidence Interval
DR-PPI
-137,280,000,000,000,000,000,000,000,000,000
-101,639,999,999,999,990,000,000,000,000,000
-66,000,000,000,000,000,000,000,000,000,000
-30,360,000,000,000,007,000,000,000,000,000
Jul 26, 2025
Confidence Interval
Updated 1mo ago
Evaluation Results
Method
Method
Links
Confidence Interval
DR-PPI
2025.07
1,820.79
IS
Protocol=CLT
2025.07
1,814.37
IS
Protocol=Bootstrap
2025.07
1,802.37
DM
2025.07
1,423.57
AugIS
Protocol=Bootstrap
2025.07
973.22
AugIS
Protocol=CLT
2025.07
970.46
AugDR
Protocol=CLT
2025.07
-35,900,000,000,000,000,000,000,000,000,000
DR
Protocol=CLT
2025.07
-132,000,000,000,000,000,000,000,000,000,000
Feedback
Search any
task
Search any
task